{"name":"kotaemon: An Open-Source RAG Tool for Document Chat","description":"kotaemon is an open-source, RAG-based tool designed to facilitate interactive conversations with your documents. It provides a clean and customizable UI, catering to both end-users seeking document Q&A and developers building RAG pipelines.","github":"https://github.com/Cinnamon/kotaemon","url":"https://osrepos.com/repo/cinnamon-kotaemon","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/cinnamon-kotaemon","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/cinnamon-kotaemon.md","json":"https://osrepos.com/repo/cinnamon-kotaemon.json","topics":["chatbot","llms","open-source","rag","Python","document-qa","ai-tools"],"keywords":["chatbot","llms","open-source","rag","Python","document-qa","ai-tools"],"stars":null,"summary":"kotaemon is an open-source, RAG-based tool designed to facilitate interactive conversations with your documents. It provides a clean and customizable UI, catering to both end-users seeking document Q&A and developers building RAG pipelines.","content":"## Introduction\nkotaemon is an open-source, RAG-based tool designed to facilitate interactive conversations with your documents. It offers a clean and customizable UI, built for both end-users who want to perform QA on their documents and developers looking to build their own RAG pipelines. This project aims to provide a functional RAG UI, supporting various LLMs, easy installation, and a robust framework for RAG pipeline development.\n\nFor end-users, kotaemon provides a clean and minimalistic UI for RAG-based QA, compatibility with various LLM API providers (OpenAI, AzureOpenAI, Cohere, etc.), and local LLMs (via `ollama` and `llama-cpp-python`), along with easy installation. Developers benefit from a comprehensive framework for building RAG pipelines, a customizable UI built with Gradio, and a dedicated Gradio theme.\n\nKey features include hosting your own document QA web-UI with multi-user login and file organization, support for various LLM and embedding models, a hybrid RAG pipeline for optimal retrieval quality, multi-modal QA support for documents with figures and tables, and advanced citations with in-browser document preview. The system also supports complex reasoning methods like question decomposition and agent-based reasoning (ReAct, ReWOO), and offers a configurable settings UI.\n\n## Installation\nTo get started with kotaemon, ensure you meet the system requirements: Python >= 3.10. Docker is optional but recommended for an easier setup. For processing additional file types beyond `.pdf`, `.html`, `.mhtml`, and `.xlsx`, you may need to install Unstructured.\n\n### With Docker (Recommended)\nkotaemon provides `lite`, `full`, and `ollama` Docker images. The `full` version includes `unstructured` for broader file type support, while `ollama` bundles Ollama for local RAG.\n\nTo run the `lite` version:\nbash\ndocker run \\\n-e GRADIO_SERVER_NAME=0.0.0.0 \\\n-e GRADIO_SERVER_PORT=7860 \\\n-v ./ktem_app_data:/app/ktem_app_data \\\n-p 7860:7860 -it --rm \\\nghcr.io/cinnamon/kotaemon:main-lite\n\nAccess the WebUI at `http://localhost:7860/`. You can specify the platform (e.g., `--platform linux/arm64`) if needed.\n\n### Without Docker\n1. Clone the repository and install required packages:\nshell\ngit clone https://github.com/Cinnamon/kotaemon\ncd kotaemon\npip install -e \"libs/kotaemon[all]\"\npip install -e \"libs/ktem\"\n\n2. Create a `.env` file based on `.env.example` in the project root for initial model configuration.\n3. (Optional) For in-browser PDF viewer, download and extract [PDF_JS_DIST](https://github.com/mozilla/pdf.js/releases/download/v4.0.379/pdfjs-4.0.379-dist.zip) to `libs/ktem/ktem/assets/prebuilt`.\n4. Start the web server:\nshell\npython app.py\n\nThe app will launch in your browser. Default login is `admin`/`admin`.\n\n## Examples\nkotaemon offers several ways to experience its capabilities:\n*   **Live Demos:** Explore interactive versions on Hugging Face Spaces:\n    *   [Live Demo #1](https://huggingface.co/spaces/cin-model/kotaemon)\n    *   [Live Demo #2](https://huggingface.co/spaces/cin-model/kotaemon-demo)\n*   **Local RAG with Colab:** Try a local RAG setup using the provided [Colab Notebook](https://colab.research.google.com/drive/1eTfieec_UOowNizTJA1NjawBJH9y_1nn).\n*   **Visual Previews:** The repository includes preview images showcasing the user interface, such as the chat tab and advanced citation features with in-browser PDF viewer.\n\n## Why Use kotaemon?\nkotaemon stands out as a powerful and flexible solution for document Q&A due to several compelling reasons:\n*   **Open-Source & Community-Driven:** Being open-source, it fosters transparency, community contributions, and continuous improvement.\n*   **Comprehensive RAG Capabilities:** It provides a robust, hybrid RAG pipeline with full-text and vector retrieval, re-ranking, and support for complex reasoning methods like question decomposition and agent-based approaches (ReAct, ReWOO).\n*   **Versatile LLM Support:** Seamlessly integrate with popular LLM API providers (OpenAI, AzureOpenAI, Cohere) or leverage local models via Ollama and `llama-cpp-python` for private RAG solutions.\n*   **User-Friendly & Customizable UI:** The clean and minimalistic Gradio-based UI is intuitive for end-users, while its extensibility allows developers to customize or add new UI elements and integrate custom RAG pipelines.\n*   **Advanced Features:** Benefit from multi-modal QA support (figures, tables), detailed citations with in-browser PDF preview and relevance scoring, and configurable settings to fine-tune retrieval and generation processes.\n*   **Easy Deployment:** With Docker support and clear installation guides, setting up your own document QA web-UI is straightforward.\n\n## Links\n*   **GitHub Repository:** [https://github.com/Cinnamon/kotaemon](https://github.com/Cinnamon/kotaemon)\n*   **Live Demo #1:** [https://huggingface.co/spaces/cin-model/kotaemon](https://huggingface.co/spaces/cin-model/kotaemon)\n*   **Live Demo #2:** [https://huggingface.co/spaces/cin-model/kotaemon-demo](https://huggingface.co/spaces/cin-model/kotaemon-demo)\n*   **Online Install:** [https://cinnamon.github.io/kotaemon/online_install/](https://cinnamon.github.io/kotaemon/online_install/)\n*   **Colab Notebook (Local RAG):** [https://colab.research.google.com/drive/1eTfieec_UOowNizTJA1NjawBJH9y_1nn](https://colab.research.google.com/drive/1eTfieec_UOowNizTJA1NjawBJH9y_1nn)\n*   **User Guide:** [https://cinnamon.github.io/kotaemon/](https://cinnamon.github.io/kotaemon/)\n*   **Developer Guide:** [https://cinnamon.github.io/kotaemon/development/](https://cinnamon.github.io/kotaemon/development/)\n*   **Feedback:** [https://github.com/Cinnamon/kotaemon/issues](https://github.com/Cinnamon/kotaemon/issues)\n*   **Contact:** [mailto:kotaemon.support@cinnamon.is](mailto:kotaemon.support@cinnamon.is)\n*   **Gradio Theme:** [https://github.com/lone17/kotaemon-gradio-theme](https://github.com/lone17/kotaemon-gradio-theme)","metrics":{"detailViews":4,"githubClicks":5},"dates":{"published":null,"modified":"2025-11-22T16:00:53.000Z"}}